List available tools with args, defaults, outputs, and examples.
AI agents call mcp_help to retrieve information from Promethean OS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that retrieves and displays information about the MCP server's available tools. It has no capability to modify, execute, delete, or transfer data. The classification as Read is appropriate given its purely informational purpose.
From the tool's definition Tool name 'mcp_help' and description 'List available tools with args, defaults, outputs, and examples' indicate information retrieval with no side effects. It queries and returns metadata about available tools.
Attacks that exploit this kind of access
List available tools with args, defaults, outputs, and examples. It is categorised as a Read tool in the Promethean OS MCP MCP Server, which means it retrieves data without modifying state.
Register the Promethean OS MCP server in PolicyLayer and add a rule for mcp_help: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Promethean OS MCP. Nothing to install.
mcp_help is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mcp_help rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for mcp_help. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
mcp_help is provided by the Promethean OS MCP server (octave-commons/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →